Garuda - Garba Rujukan Digital

Sistem Pakar Diagnosa Penyakit Pada Sugar Glider Dengan Metode Forward Chaining Berbasis Web Alvenio Farhan Prayogo; Fatkhul Amin
JURNAL MAHAJANA INFORMASI Vol 6 No 2 (2021): JURNAL MAHAJANA INFORMASI
Publisher : Universitas Sari Mutiara Indonesia Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51544/jurnal mi.v6i2.2257

Sugar Glider, Forward Chaining, Disease, Expert System An expert system is a computer-based application that uses knowledge, facts, and reasoning techniques to solve problems as thought by experts. Expert systems provide added value to technology to help solve problems in the health sector (Kusrini, 2006). Sugar Glider (Petaurus Breviceps) is a marsupial mammal that is active at night (nocturnal). Keeping a Sugar Glider must require good and correct care to avoid all diseases. Based on these problems, this study aims to build an expert system that is able to combine the knowledge of an expert with artificial intelligence technology to diagnose disease in Sugar Glider. By referring to the formulation of the problem, this study aims to build an expert system design to diagnose diseases in Sugar Glider that are maintained by adopters or caretakers. Research conducted by researchers is related to the Forward Chaining method as well as information about diseases in Sugar Glider. The method used in the development of this system is the Linear Sequential Model or commonly called the waterfall model. The data used in this study were obtained from several collected references. From these data in this study resulted in an accuracy of 87.5% by testing 8 times of the application made. An expert system for diagnosing diseases in sugar gliders can make it easier for users to diagnose diseases.

Analisis Sentimen Evaluasi Pembelajaran Tatap Muka 100 Persen pada Pengguna Twitter menggunakan Metode Logistic Regression Saiful Anwar Assaidi; Fatkhul Amin
Jurnal Pendidikan Tambusai Vol. 6 No. 2 (2022): Agustus 2022
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Perkembangan Machine learning semakin pesat seiring dengan bertambah banyaknya data yang ada di internet terutama dari media sosial seperti facebook, twitter dan Instagram. Diantara banyak topik yang dibahas di media sosial, topik tentang Evaluasi Pembelajaran Tatap Muka (PTM) serratus persen di indonesia sempat hangat. Banyak masyarakat yang berpendapat mengenai evaluasi PTM terutama di media sosial twiter. banyaknya data yang tidak teratur dan berbeda pola serta makna sehingga sulit mengetahui pendapat yang disampaikan tersebut termasuk pendapat positif yang pro terhadap PTM atau sebaliknya, negatif yang kontra terhadap PTM. Machine Learning bisa mengolah data yang banyak dan tidak teratur untuk menghasilkan sebuah output dengan cepat. Tujuan penelitian ini agar menghasilkan sebual model yang dapat membantu mengklasifikasi opini masyarakat terkait topik evaluasi Pembelajaran Tatap Muka (PTM) seratus persen kedalam sentiment negatif atau positif, biasa disebut dengan analisis sentimen. Klasifikasi termasuk dalam jenis supervised learning dalam machine learning. Logistic Regression merupakan metode machine learning yang dapat digunakan untuk membuat model Klasifikasi yang bisa digunakan untuk melakukan analisis sentimen. Hasil dari Analisis Sentimen menggunakan metode Logistic Regression pada penelitian ini menghasilkan nilai accuracy sebesar 78,57%, precision 76,92%, recall 83,3 % dan nilai F1-Score sebesar 80%.

Perancangan Alat Pendeteksi Asap dan Suhu Ruangan Berbasis Internet Of Think di PT. APAC Inti Corpora Indra Ava Dianta; Moh Muthohir; Ilham Ramasyahdani; Fatkhul Amin
Elkom : Jurnal Elektronika dan Komputer Vol 15 No 2 (2022): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v15i2.859

In this final project the author discusses the problem entitled "Design of Smoke Detector and Room Temperature of SAP ERP Server at PT Apac Inti Corpora". This design aims to support the improvement of the security system in the server room with smoke and temperature detectors and microcontroller-based automatic countermeasures. Against the background of problems with sensors and countermeasures systems in the server room and lack of insight into sensor installation. This tool uses a gas sensor MQ-2 as a smoke detector, a DHT-11 sensor as a temperature detector, Arduino as a microcontroller that controls I/O, buzzer and LED as an alarm, a fan as a temperature controller, and an LCD to display conditions in the room. The output of the MQ-2 and DHT-11 sensors will be processed in a programmed microcontroller so that it can display conditions on the LCD. This tool will turn on the alarm and fan if smoke and high temperature are detected at the specified conditions.

Rancang Bangun Validitas Dokumen Elektronik Menggunakan Metode Algoritma RSA dan AES Mokhammad Iqbal; Fatkhul Amin
IJAI (Indonesian Journal of Applied Informatics) Vol 6, No 2 (2022)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v6i2.73156

Abstrak Tanda tangan digital adalah skema matematis untuk memverifikasi keaslian suatu pesan atau dokumen digital sehingga keberadaan tanda tangan digital pada suatu dokumen elektronik dapat menunjukkan keaslian suatu dokumen yang dijamin. Dokumen elektronik ini tetap merupakan dokumen resmi yang penting seperti dokumen cetak. Tanda tangan digital sangat bergantung pada isi dokumen yang ditandatangani, sehingga setiap dokumen akan menghasilkan tanda tangan digital yang berbeda dengan dokumen lainnya. Perkembangan teknologi memungkinkan untuk dilakukan pembuktian matematis, dimana informasi yang diperoleh satu pihak dari pihak lain dapat ditentukan untuk menjamin keaslian informasi atau dokumen elektronik yang diterima. Tanda tangan digital yang dirancang pada penelitian ini mengimplementasikan QR-Code, fungsi hashing MD5 dan algoritma yang akan ditambahkan adalah kombinasi enkripsi RSA dan AES dengan ukuran blok 256 bit.AbstractDigital signature is a mathematical scheme to verify the authenticity of a message or digital document so that the presence of a digital signature on an electronic document can indicate the authenticity of a guaranteed document. These electronic documents remain as important official documents as printed documents. Digital signatures are very dependent on the contents of the signed document, so each document will produce a digital signature that is different from other documents. Technological developments make it possible to do mathematical proofs, where information obtained by one party from another can be determined to ensure the authenticity of the information or electronic documents received. The digital signature designed in this study implements a QR-Code, MD5 hashing function and the algorithm that will be added is a combination of RSA and AES encryption with a block size of 256 bits.

MONITORING LOAD BALANCING SERVER E-LEARNING UNISBANK MENGGUNAKAN METODE LEAST Dwi Budi Santoso; Jeffri Alfa Razaq; Fatkhul Amin Amin
Elkom : Jurnal Elektronika dan Komputer Vol 16 No 1 (2023): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v16i1.932

Implementation of Distance Learning (PJJ) is effective in the teaching and learning process during the pandemic. This is supported by Unisbank students in mastering information technology. PJJ technology, also known as e-learning, is a bridge between lecturers and students in the process of meeting in class into a meeting process in cyberspace. E-learning becomes ineffective when the demand for e-learning usage is high, causing server overload or crashes. When the e-learning server is overloaded, all parts that are usually connected and interrelated, such as lecturers, students, administration and others, become disconnected. The importance of monitoring the e-learning server to keep the e-learning load under control, and the server that has a lot of load will be divided so that e-learning will run smoothly and not be overloaded. Monitoring the Elearning server with the Least Connection method is applied to the Unisbank e-learning server and makes e-learning not overloaded. The results of the load balancer workload test with 1000 connections, the resulting response time is 0.2 ms, the workload is 5000 connections, the response time is 0.2 ms and the workload is 10,000 connections, the resulting reply time is 0.2 ms.

Penerapan Kemiripan Dokumen pada Mesin Pencari Menggunakan Metode Hellinger Fatkhul Amin; Eko Nur Wahyudi; Budi Hartono
Jurnal Rekayasa Industri (JRI) Vol. 5 No. 2 (2023)
Publisher : Program Studi Teknik Industri, Fakultas Sains dan Teknologi, Universitas Widya Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37631/jri.v5i2.985

Penerapan alat pendeteksi kemiripan dokumen teks bahasa Indonesia dibuat untuk bisa menunjukkan seberapa tingkat pebedaan antar dokumen teks yang digunakan untuk mengurangi plagiarism. Model pendeteksi kemiripan dokumen menggunakan metode algoritma Hellinger yang ditujukan untuk menghasilkan tingkat akurasi yang tinggi. Proses Pra Perhitungan hellinger dilakukan tahap-tahap tokenisasi, penyaringan dan pembuatan akar kata. Penyaringan menggunakan stopword tala dan proses pembuatan akar kata menggunakan metode rule base stemmer bahasa Indonesia. Proses uji alat pendeteksi kemiripan didahului dengan uji persepsi menggunakan kamus besar bahasa indonesia untuk menetapkan kata yang dicari relevan atau tidak relevan. Hasil akhir pengujian alat pendeteksi kemiripan dokumen menggunakan metode Hellinger didapatkan tingkat akurasi rata-rata 0,71 dan tingkat rata-rata dokumen terambil 0,31.

Perancangan Sistem Rekomendasi Laptop dengan Model Prototyping dan Penerapan Content-Based Filtering Approach pada ELS Computer Shop Semarang Riandy Oktavian; Fatkhul Amin
G-Tech: Jurnal Teknologi Terapan Vol 8 No 1 (2024): G-Tech, Vol. 8 No. 1 Januari 2024
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/gtech.v8i1.3490

A recommendation system is a software technique that provides suggestions orrecommendations based on user preferences. This paper examines arecommendation system for laptops at Els Computer Shop in Semarang, usinga content-based filtering approach to help customers select laptops that matchthe attributes they are looking for. The prototype method was chosen as thesystem development technique because it facilitates interaction between systemdevelopers and can address issues between users and analysts. The design of thisrecommendation system involves two types of data encoding: one-hot encodingand ordinal encoding. One-hot encoding transforms categorical laptop data intobinary numbers (0 or 1), while ordinal encoding converts categorical laptopdata based on a specific order into numeric values (0, 1, 2, 3). The transformeddata is then calculated using cosine similarity to determine the similarity scoreof recommended laptops. The results of the laptop recommendation systemdisplay three laptops that are most similar to the searched laptop index basedon cosine similarity calculations.

Perancangan Alat Pendeteksi Asap dan Suhu Ruangan Berbasis Internet Of Think di PT. APAC Inti Corpora Indra Ava Dianta; Moh Muthohir; Ilham Ramasyahdani; Fatkhul Amin
Elkom : Jurnal Elektronika dan Komputer Vol 15 No 2 (2022): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v15i2.859

In this final project the author discusses the problem entitled "Design of Smoke Detector and Room Temperature of SAP ERP Server at PT Apac Inti Corpora". This design aims to support the improvement of the security system in the server room with smoke and temperature detectors and microcontroller-based automatic countermeasures. Against the background of problems with sensors and countermeasures systems in the server room and lack of insight into sensor installation. This tool uses a gas sensor MQ-2 as a smoke detector, a DHT-11 sensor as a temperature detector, Arduino as a microcontroller that controls I/O, buzzer and LED as an alarm, a fan as a temperature controller, and an LCD to display conditions in the room. The output of the MQ-2 and DHT-11 sensors will be processed in a programmed microcontroller so that it can display conditions on the LCD. This tool will turn on the alarm and fan if smoke and high temperature are detected at the specified conditions.

MONITORING LOAD BALANCING SERVER E-LEARNING UNISBANK MENGGUNAKAN METODE LEAST Dwi Budi Santoso; Jeffri Alfa Razaq; Fatkhul Amin Amin
Elkom : Jurnal Elektronika dan Komputer Vol 16 No 1 (2023): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v16i1.932

Implementation of Distance Learning (PJJ) is effective in the teaching and learning process during the pandemic. This is supported by Unisbank students in mastering information technology. PJJ technology, also known as e-learning, is a bridge between lecturers and students in the process of meeting in class into a meeting process in cyberspace. E-learning becomes ineffective when the demand for e-learning usage is high, causing server overload or crashes. When the e-learning server is overloaded, all parts that are usually connected and interrelated, such as lecturers, students, administration and others, become disconnected. The importance of monitoring the e-learning server to keep the e-learning load under control, and the server that has a lot of load will be divided so that e-learning will run smoothly and not be overloaded. Monitoring the Elearning server with the Least Connection method is applied to the Unisbank e-learning server and makes e-learning not overloaded. The results of the load balancer workload test with 1000 connections, the resulting response time is 0.2 ms, the workload is 5000 connections, the response time is 0.2 ms and the workload is 10,000 connections, the resulting reply time is 0.2 ms.

Impelementasi Chatbot Menggunakan Framework Rasa Untuk Melayani Informasi Produk Umkm Di Kab.Kendal Dehan Setya Ramadhan; Fatkhul Amin
INTECOMS: Journal of Information Technology and Computer Science Vol 6 No 2 (2023): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/intecoms.v6i2.7571

Penelitian ini membahas pengembangan chatbot dengan framework Rasa untuk memberikan informasi produk umkm di Kabupaten Kendal. kendala yang dihadapi seperti kurangnya informasi produk umkm yang dibutuhkan masyarakat. maka untuk mengatasi masalah yang ada dibuatlah sebuah sistem kecerdasan buatan pada layanan informasi produk umkm yaitu chatbot dilengkapi dengan kemampuan bahasa alami untuk memahami permintaan user dan memberikan informasi produk yang ditanyakan. Dengan framework Rasa.ai ini kita dimudahkan oleh platform open source seperti bisa integritas dengan platform sosial media. Dalam penelitian ini menggunakan metode wawancara, observasi, dan studi pustaka yaitu proses arahan landasan teori untuk mengidentifikasi sumber literatur yang relevan seperti jurnal ilmiah. Pengembangan chatbot menggunakan framework Rasa.ai mendapat tingkat akurasi sebesar 1.00 dibuktikan dari hasil running sistem chatbot yang telah dibuat. Proses pengujian dilakukan dengan cara memasukkan pertanyaan sehingga chatbot akan memberikan jawaban sesuai yang ditanyakan user seputar informasi produk umkm di kab.Kendal.

Title

Found 30 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 30 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 30 Documents
Search